AEAlan Erera

Alan Erera

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Alan Erera has a total of 31 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Integrating order-to-delivery time sensitivity in e-commerce middle-mile consolidation network design

    by Lacy M. Greening, Jisoo Park, Mathieu Dahan, Alan L Erera, Benoit Montreuil


  • Outbound Load Planning in Parcel Delivery Service Networks Using Machine Learning and Optimization

    by Ritesh Ojha, Wenbo Chen, Hanyu Zhang, Reem Khir, Alan Erera, Pascal Van Hentenryck

    The load planning problem is a critical challenge in service network design for parcel carriers: it decides how many trailers (or loads), perhaps of different types, to assign for dispatch over time between pairs of terminals. Another key challenge is to determine a flow plan that specifies how parcel volumes are assigned to planned loads. This paper considers the Outbound Load Planning Problem (OLPP) that considers flow and load planning challenges jointly to adjust loads and flows as demand forecast changes over time before the day of terminal operations. The paper develops a decision support tool to inform planners making these decisions at terminals across the network. It formulates the OLPP as a mixed-integer programming (MIP) model and shows that it admits a large number of symmetries in a network where each commodity can be routed through primary and alternate terminals. As a result, an optimization solver may return fundamentally different solutions to closely related problems (i.e., OLPPs with slightly different inputs), confusing planners and reducing trust in optimization. To remedy this limitation, the first contribution of the paper is to propose a lexicographical optimization approach that eliminates those symmetries by generating optimal solutions while staying close to a reference plan. The second contribution of the paper is the design of an optimization proxy that addresses the computational challenges of the optimization model. The optimization proxy combines a machine learning model and an MIP-based repair procedure to find near-optimal solutions that satisfy real-time constraints imposed by planners in the loop. An extensive computational study on industrial instances shows that the optimization proxy is around 10 times faster than the commercial solver in obtaining solutions of similar quality; the optimization proxy is also orders of magnitude faster for generating solutions that are consistent with each other. The proposed approach also demonstrates the benefits of the OLPP for load consolidation and the significant savings obtained from combining machine learning and optimization. Funding: This work was supported by the NSF AI Institute for Advances in Optimization [Grant Award 2112533]. Supplemental Material: The online appendix is available at https://doi.org/10.1287/trsc.2024.0672 .


  • Open Access

    SPOT: Spatio-Temporal Pattern Mining and Optimization for Load Consolidation in Freight Transportation Networks

    by Sikai Cheng, Amira Hijazi, Jeren Konak, Alan Erera, Pascal Van Hentenryck

    Freight consolidation has significant potential to reduce transportation costs and mitigate congestion and pollution. An effective load consolidation plan relies on carefully chosen consolidation points to ensure alignment with existing transportation management processes, such as driver scheduling, personnel planning, and terminal operations. This complexity represents a significant challenge when searching for optimal consolidation strategies. Traditional optimization-based methods provide exact solutions, but their computational complexity makes them impractical for large-scale instances and they fail to leverage historical data. Machine learning-based approaches address these issues but often ignore operational constraints, leading to infeasible consolidation plans. This work proposes SPOT, an end-to-end approach that integrates the benefits of machine learning (ML) and optimization for load consolidation. The ML component plays a key role in the planning phase by identifying the consolidation points through spatio-temporal clustering and constrained frequent itemset mining, while the optimization selects the most cost-effective feasible consolidation routes for a given operational day. Extensive experiments conducted on industrial load data demonstrate that SPOT significantly reduces travel distance and transportation costs (by about 50% on large terminals) compared to the existing industry-standard load planning strategy and a neighborhood-based heuristic. Moreover, the ML component provides valuable tactical-level insights by identifying frequently recurring consolidation opportunities that guide proactive planning. In addition, SPOT is computationally efficient and can be easily scaled to accommodate large transportation networks.

  • Open Access

    Optimization-based Learning for Dynamic Load Planning in Trucking Service Networks

    by Ritesh Ojha, Wenbo Chen, Hanyu Zhang, Reem Khir, Alan Erera, Pascal Van Hentenryck

    The load planning problem is a critical challenge in service network design for parcel carriers: it decides how many trailers to assign for dispatch over time between pairs of terminals. Another key challenge is to determine a flow plan, which specifies how parcel volumes are assigned to planned loads. This paper considers the Outbound Load Planning Problem (OLPP) that considers flow and load planning challenges jointly in order to adjust loads and flows as the demand forecast changes over time before the day of operations in a terminal. The paper aims at developing a decision-support tool to inform planners making these decisions at terminals across the network. The paper formulates the OLPP as a mixed-integer programming model and shows that it admits a large number of symmetries in a network where each commodity can be routed through primary and alternate terminals. As a result, an optimization solver may return fundamentally different solutions to closely related problems, confusing planners and reducing trust in optimization. To remedy this limitation, this paper proposes a lexicographical optimization approach that eliminates those symmetries by generating optimal solutions staying close to a reference plan. Moreover, this paper designs an optimization proxy that addresses the computational challenges of the optimization model. The optimization proxy combines a machine-learning model and a repair procedure to find near-optimal solutions that satisfy real-time constraints imposed by planners in the loop. An extensive computational study on industrial instances shows that the optimization proxy is orders of magnitude faster for generating solutions that are consistent with each other. The proposed approach also demonstrates the benefits of the OLPP for load consolidation and the significant savings obtained from combining machine learning and optimization.

  • Dynamic Courier Capacity Acquisition in Rapid Delivery Systems: A Deep Q-Learning Approach

    by Ramon Auad, Alan Erera, Martin Savelsbergh

    With the recent boom of the gig economy, urban delivery systems have experienced substantial demand growth. In such systems, orders are delivered to customers from local distribution points respecting a delivery time promise. An important example is a restaurant meal delivery system, where delivery times are expected to be minutes after an order is placed. The system serves orders by making use of couriers that continuously perform pickups and deliveries. Operating such a rapid delivery system is very challenging, primarily because of the high service expectations and the considerable uncertainty in both demand and delivery capacity. Delivery providers typically plan courier shifts for an operating period based on a demand forecast. However, because of the high demand volatility, it may at times during the operating period be necessary to adjust and dynamically add couriers. We study the problem of dynamically adding courier capacity in a rapid delivery system and propose a deep reinforcement-learning approach to obtain a policy that balances the cost of adding couriers and the cost-of-service quality degradation because of insufficient delivery capacity. Specifically, we seek to ensure that a high fraction of orders is delivered on time with a small number of courier hours. A computational study in the meal delivery space shows that a learned policy outperforms policies representing current practice and demonstrates the potential of deep learning for solving operational problems in highly stochastic logistic settings. History: This paper has been accepted for the Transportation Science Special Issue on Machine-Learning Methods and Applications in Large-Scale Route Planning Problems. Funding: This work was supported by Agencia Nacional de Investigación y Desarrollo [72180404]. Supplemental Material: The e-companion is available at https://doi.org/10.1287/trsc.2022.0042 .


  • Near real-time loadplan adjustments for less-than-truckload carriers

    by Ian Herszterg, Yassine Ridouane, Natashia Boland, Alan Erera, Martin Savelsbergh


  • Open Access

    Dynamic service area sizing in urban delivery

    by Marlin W. Ulmer, Alan Erera, Martin Savelsbergh

    We consider an urban instant delivery environment, e.g., meal delivery, in which customers place orders over the course of a day and are promised delivery within a short period of time after an order is placed. Deliveries are made using a fleet of vehicles, each completing one or more trips during the day. To avoid missing delivery time promises as much as possible, the provider manages demand by dynamically adjusting the size of the service area, i.e., the area in which orders can be delivered. The provider seeks to maximize the number of orders served while avoiding missed delivery time promises. We present three techniques to support the dynamic adjusting of the size of the service area which can be embedded in planning and execution tools that help the provider achieve its goal. First, we learn the functional dependency between expected demand and the service area that can be supported with the fleet of vehicles. Second, we use value function approximation to improve an initial service area sizing plan for the day based on expected demand. Finally, we introduce a correction mechanism to dynamically adjust the service area sizing plan in response to observed realized demand. Extensive computational experiments demonstrate the efficacy of the techniques and show that dynamic sizing of the service area can increase the number of orders served significantly without increasing the number of missed delivery time promises.


  • Motor Carrier Service Network Design

    by Ilke Bakir, Alan Erera, Martin Savelsbergh


  • Sampling Scenario Set Partition Dual Bounds for Multistage Stochastic Programs

    by Ilke Bakir, Natashia Boland, Brian Dandurand, Alan Erera

    We consider multistage stochastic programming problems in which the random parameters have finite support, leading to optimization over a finite scenario set. There has been recent interest in dual bounds for such problems, of two types. One, known as expected group subproblem objective (EGSO) bounds, require solution of a group subproblem, which optimizes over a subset of the scenarios, for all subsets of the scenario set that have a given cardinality. Increasing the subset cardinality in the group subproblem improves bound quality, (EGSO bounds form a hierarchy), but the number of group subproblems required to compute the bound increases very rapidly. Another is based on partitions of the scenario set into subsets. Combining the values of the group subproblems for all subsets in a partition yields a partition bound. In this paper, we consider partitions into subsets of (nearly) equal cardinality. We show that the expected value of the partition bound over all such partitions also forms a hierarchy. To make use of these bounds in practice, we propose random sampling of partitions and suggest two enhancements to the approach: sampling partitions that align with the multistage scenario tree structure and use of an auxiliary optimization problem to discover new best bounds based on the values of group subproblems already computed. We establish the effectiveness of these ideas with computational experiments on benchmark problems. Finally, we give a heuristic to save computational effort by ceasing computation of a partition partway through if it appears unpromising.